arXiv subjects

Guillaume Vimont

Publications and source records attributed to Guillaume Vimont.

4 recordsLinked to original sources

arXiv2026

HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction

Authorship attribution asks whether two pieces of text share a writer, but topical confound makes the task deceptively easy: two authors covering the same topic may look more alike than one author covering two topics. Scholarly prose offers a natural remedy, academic writers produce multiple papers on related but distinct topics while maintaining consistent stylistic habits. We introduce HALvest, a 17-billion-token multilingual corpus of open-access academic papers, and its English contrastive derivative HALvest-Contrastive, where same-author passages are drawn from distinct papers within a disciplinary field to minimize topical overlap. We validate our benchmark by showing that a strong lexical baseline collapses once topical shortcuts are removed. On this same benchmark, we revisit how authorship is scored. Standard systems compress each document into a single vector. We instead keep a sequence of vectors and compare them with late interaction, then propose patch-level late interaction, which groups neighboring tokens into patches before matching. Matching at the sequence level greatly improves performance over the single-vector baseline, but the optimal interaction granularity is subtle.

cs.DL↗

arXiv2026

Where Does Authorship Signal Emerge in Encoder-Based Language Models?

Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap. Stylistic features such as word length, punctuation density, and function-word frequency are similarly available at every layer in every model we probe, including an off-the-shelf control encoder, suggesting that the gap is not explained by their linear readability. Instead, causal intervention shows that the scorer appears to determine where the encoder consolidates authorship signal. Mean pooling forces consolidation by early to mid layers, while late interaction defers it to later layers. We further derive this difference from the gradient structure of each scorer, and training dynamics reveal distinct learning trajectories that follow from that difference.

cs.CL↗

arXiv2018

The content correlation of multiple streaming edges

We study how to detect clusters in a graph defined by a stream of edges, without storing the entire graph. We extend the approach to dynamic graphs defined by the most recent edges of the stream and to several streams. The {\em content correlation }of two streams $ρ(t)$ is the Jaccard similarity of their clusters in the windows before time $t$. We propose a simple and efficient method to approximate this correlation online and show that for dynamic random graphs which follow a power law degree distribution, we can guarantee a good approximation. As an application, we follow Twitter streams and compute their content correlations online. We then propose a {\em search by correlation} where answers to sets of keywords are entirely based on the small correlations of the streams. Answers are ordered by the correlations, and explanations can be traced with the stored clusters.

cs.LO↗

arXiv2017

Approximate Integration of streaming data

We approximate analytic queries on streaming data with a weighted reservoir sampling. For a stream of tuples of a Datawarehouse we show how to approximate some OLAP queries. For a stream of graph edges from a Social Network, we approximate the communities as the large connected components of the edges in the reservoir. We show that for a model of random graphs which follow a power law degree distribution, the community detection algorithm is a good approximation. Given two streams of graph edges from two Sources, we define the {\em Community Correlation} as the fraction of the nodes in communities in both streams. Although we do not store the edges of the streams, we can approximate the Community Correlation and define the {\em Integration of two streams}. We illustrate this approach with Twitter streams, associated with TV programs.

cs.SI↗